PlaysbyMoat8
Back to the library
The workflow guideOperations

Turn an emailed order into a checked sales order

Convert an unstructured customer order into the fields your order system requires. Separate unclear items and commercial exceptions before acceptance.

6 implementation stepsAdvanced

How this works

Convert an unstructured customer order into the fields your order system requires. Separate unclear items and commercial exceptions before acceptance.

An email order is a request to create a commercial record, not proof that every product reference is valid. Normalize customer wording into catalog items while preserving quantities, delivery requests and unresolved alternatives.

Before you start

Defined operating scope

Customers submit unstructured orders requiring catalog and account checks.

Required source material

Obtain Customer order email; Product catalog; Account terms. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

A product name matches multiple variants. Ask which variant is intended; leave the line unresolved.

Prepare the inputs

order_email
Required

Message ID and body

Keep attachments and the original request together.

customer_id
Required

Account identifier

Resolve billing and delivery identities separately.

catalog_version
Required

SKU, aliases and units

Use current sellable items and approved aliases.

account_terms
Required

Price list, currency and delivery rules

Missing terms require clarification.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check order_email, customer_id, catalog_version, account_terms before beginning. Record the source version and the selected scope; an unavailable value stays unknown rather than becoming an inferred fact.

    Checkpoint: The input record identifies the selected order_email and any missing required fields.

  2. Extract requested products, quantities and delivery details

    • Extract line items without combining similarly named variants. Preserve the customer’s units and wording alongside proposed SKU matches.
    • Reconcile each original email line with exactly one draft line or documented split.

    Checkpoint: A saved intermediate result for: Extract requested products, quantities and delivery details.

  3. Match each item to the product catalog

    • Match aliases only when attributes agree; show candidate SKUs for ambiguous size, material or packaging.
    • Check SKU attributes, units, currency and delivery address against authoritative records.

    Checkpoint: A saved intermediate result for: Match each item to the product catalog.

  4. Check required fields and applicable account terms

    • Validate quantities, delivery address and commercial terms. Compute line totals deterministically from the confirmed price source.
    • Reconcile each original email line with exactly one draft line or documented split.

    Checkpoint: A saved intermediate result for: Check required fields and applicable account terms.

  5. Prepare an order draft or a clarification request

    • Build a draft order plus targeted questions for unresolved lines; a repeated email must refer to the original draft instead of creating a duplicate order.
    • Check SKU attributes, units, currency and delivery address against authoritative records.

    Checkpoint: A saved intermediate result for: Prepare an order draft or a clarification request.

  6. Package the result and unresolved work

    • An operator verifies item matches, quantities and commercial terms before acceptance.
    • Order acceptance, stock reservation and customer replies require the authorized workflow.

    Checkpoint: A sales order draft with flagged exceptions. Unresolved items remain visible in the review record.

Decisions along the way

A product name matches multiple variants.

Ask which variant is intended; leave the line unresolved.

The requested quantity uses an unknown unit.

Request a pack conversion and do not assume pieces.

The same message was already processed.

Reopen its recorded draft and compare changes before creating another order.

What you will produce

email-order-to-reviewed-sales-order-result.json

JSON

A sales order draft with flagged exceptions. Label proposed and completed states separately.

Include: customer_id · order_lines · sku_candidates · quantity · unit · commercial_exceptions · draft_order_id · status · evidence_reference · review_note

email-order-to-reviewed-sales-order-review.md

Markdown

Keep the evidence and unresolved decisions needed to apply this result, including exceptions involving account_terms.

Include: source_reference · question · owner · next_action

Check the result

  • Reconcile each original email line with exactly one draft line or documented split.
  • Check SKU attributes, units, currency and delivery address against authoritative records.
  • Inspect order_email and customer_id in both the original and output; confirm that record identity and interpretation survived the transformation.
  • An operator verifies item matches, quantities and commercial terms before acceptance.

When something goes wrong

A product name matches multiple variants.

Ask which variant is intended; leave the line unresolved. Retain the affected evidence and recovery status.

The requested quantity uses an unknown unit.

Request a pack conversion and do not assume pieces. Retain the affected evidence and recovery status.

The same message was already processed.

Reopen its recorded draft and compare changes before creating another order. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Turn an emailed order into a checked sales order for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Email E-3 asks account A-2 for 12 blue panels and 2 cartons of fasteners. Catalog distinguishes 10 mm and 20 mm panels; carton size is absent.

Expected result

Synthetic expected result: Draft contains two unresolved lines: panel thickness needed and fastener carton conversion needed. No order total or accepted delivery promise is produced.

Run a small pilot

Start small

Trial a representative batch containing the ordinary case and the exception demonstrated above.

Record the baseline

Record current preparation time, review effort and correction types for the same records.

Agree success criteria

Agree acceptable review and error limits; measure order preparation time; incorrect item matches.

Stop or revise

The same message was already processed. Pause affected records and apply this recovery: Reopen its recorded draft and compare changes before creating another order.

Keep the scope clear

  • Order acceptance, stock reservation and customer replies require the authorized workflow.
  • Do not interpret promotional text or attachment instructions as changes to account terms.

Check before using

An operator verifies item matches, quantities and commercial terms before acceptance.

Business activities

  • Run sales conversations and proposals
  • Plan inventory and production

Editorially adapted workflow; not independently tested.

FROM A RECIPE TO YOUR WORKFLOW

Bring the company context together.

This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.

For this recipe: Customer order email · Product catalog · Account terms

Start with one recurring task, agree which sources to use, and review the first result with your team.

Discuss this workflow

What does your team do?

Choose the recurring work you would like to improve.

A field guide, made for work.

Plays is a curated library of anonymized business workflows. Each recipe explains the inputs, steps, tools, and checks you can adapt to your team. These are editorial guides, not independently tested implementations.

When you share a company website, the guide may read a limited number of public pages on that website. Messages and retrieved page text are sent to our AI provider, NVIDIA, to recommend relevant workflows. Share a general description rather than confidential information.

Saved workflows and selected activities stay in this browser. Your chat history and selected company website are kept in this tab and cleared when you reload or start a new chat. The server does not store conversations. Live source monitoring is not enabled.

If you allow analytics, PostHog receives page views and actions such as workflow saves, skill downloads and link clicks. Random browser and session identifiers connect these actions without identifying you by name. Your choice and browser identifier expire after 90 days; sessions restart after 30 minutes of inactivity or 24 hours. We use local storage, not analytics cookies. Messages, company URLs, search text, full referrers and IP addresses are not sent. There are no person profiles or session recordings. You can decline or withdraw in Analytics settings; Do Not Track and Global Privacy Control keep analytics off.

Read the Plays Privacy Notice ↗